初始化项目，由ModelHub XC社区提供模型

Model: bartowski/LiquidAI_LFM2-350M-Extract-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,72 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+ 
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+LiquidAI_LFM2-350M-Extract-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Extract-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Extract-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Extract-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Extract-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Extract-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Extract-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Extract-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Extract-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Extract-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Extract-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Extract-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Extract-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Extract-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Extract-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Extract-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Extract-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Extract-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Extract-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Extract-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Extract-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Extract-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Extract-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2-350M-Extract-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text

LiquidAI_LFM2-350M-Extract-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:389407faeba7d8f74c762c58e7bd3f15bfe1c413bd9aa8b2b6da7149416094bd
+size 142877248

LiquidAI_LFM2-350M-Extract-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a01750ac6b36d588c1ea6dde7d161106f73abb5aaa26637c10eb8591750c8f56
+size 183657024

LiquidAI_LFM2-350M-Extract-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a518bcf3a4be2314a3d4280329f6973ed37a536eba7e1f5e47791bb1c0f1d78
+size 175399488

LiquidAI_LFM2-350M-Extract-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed70f66a1ca5ff887b0fa09fce2656125680b482a70e46105a02cd5293c2aea5
+size 158474816

LiquidAI_LFM2-350M-Extract-IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7598697359336c99ca7153c8fc584580df4e7d35ea19b5df0db972e96e5e0a14
+size 219308608

LiquidAI_LFM2-350M-Extract-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd3a5fe8493b13eaa044d39b1a59bcfcaae31374cb52f4dc986936029061ca5c
+size 210330176

LiquidAI_LFM2-350M-Extract-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff5e4dd2e7ecfa40622e4d7a6357ac1c486b990c57ff49431a21624685936426
+size 160596544

LiquidAI_LFM2-350M-Extract-Q2_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68b9cf4fe5bee5aa3be54531adbe7deb85aee9167c02c8c13797b65b55494da5
+size 176849472

LiquidAI_LFM2-350M-Extract-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9ba5d27626660414057bc3a5ac8a74067dbe48d0901b0eef610249728f22bf8
+size 203047488

LiquidAI_LFM2-350M-Extract-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af22d155c55e85ab6022b1a1c6e0568a817919135f72d4059ab8448dcc7019a3
+size 193151552

LiquidAI_LFM2-350M-Extract-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:273b1f3f63eee0e6c33f9aa8e69501f3033255783d011f800e23c848bdc27d22
+size 181150272

LiquidAI_LFM2-350M-Extract-Q3_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a4372c4f3478c1800d0326b19c737645a77040a07903f9e864c9e7eedae6e88
+size 219300416

LiquidAI_LFM2-350M-Extract-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4b7eff07349e5d88015c4f16232f9b0dfa89afdfe2f14f8826f899c478caca7
+size 219898432

LiquidAI_LFM2-350M-Extract-Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dd9d95aaeea44fdbd2b602d020cd0b29bbfa177488fe685fac04fc244a28f87
+size 237265472

LiquidAI_LFM2-350M-Extract-Q4_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:230c63a35fedd75d383af40ddb32809a00ffeb7c5b4cf538d0baa1b5f3277ec4
+size 245563968

LiquidAI_LFM2-350M-Extract-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:340a7fb24b98a7dbe933169dbbb869f4d89f8c7bf27ee45d62afabfc5b376743
+size 229311040

LiquidAI_LFM2-350M-Extract-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74cb86c0c038e7e45a498d2dd0f2eaf519583590120da01c8d63ee6cecab4653
+size 220750400

LiquidAI_LFM2-350M-Extract-Q5_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23524b3a723c4504646f4fddf9da188e6e1bac03237ec350036949152780810f
+size 276628032

LiquidAI_LFM2-350M-Extract-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e53777a7826cc5ff741d19bb95731714da593bbe9b928b891c540acd7c5885d7
+size 260375104

LiquidAI_LFM2-350M-Extract-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a1bea9bd1f2a6e75036bdd0387fefc0861e76c6f639474adf4cfbce27ddc9f5
+size 255222336

LiquidAI_LFM2-350M-Extract-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55cf3fafd382970d7bcda49ead98ac8a8c585b324d6a4491ee90bcc1817aa593
+size 293380672

LiquidAI_LFM2-350M-Extract-Q6_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afd79bd0efb7c60d43e47d0f35af7479878ae6891b5a10c3a4592a795ba66926
+size 309633600

LiquidAI_LFM2-350M-Extract-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2723a24792da9d64f2a1f6b9661c13b52194843150125f524b8c4e78d6d1747d
+size 379216448

LiquidAI_LFM2-350M-Extract-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:048aa54285a04e70338b70fbae6d5943cd3d0ffca62ca90dac2cf7f0e85cc90e
+size 711483680

README.md

@@ -0,0 +1,164 @@
+---
+quantized_by: bartowski
+pipeline_tag: text-generation
+base_model_relation: quantized
+base_model: LiquidAI/LFM2-350M-Extract
+---
+
+## Llamacpp imatrix Quantizations of LFM2-350M-Extract by LiquidAI
+
+Using <a href="https://github.com/ggml-org/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggml-org/llama.cpp/releases/tag/b6683">b6683</a> for quantization.
+
+Original model: https://huggingface.co/LiquidAI/LFM2-350M-Extract
+
+All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) combined with a subset of combined_all_small.parquet from Ed Addario [here](https://huggingface.co/datasets/eaddario/imatrix-calibration/blob/main/combined_all_small.parquet)
+
+Run them in [LM Studio](https://lmstudio.ai/)
+
+Run them directly with [llama.cpp](https://github.com/ggml-org/llama.cpp), or any other llama.cpp based project
+
+## Prompt format
+
+No prompt format found, check original model page
+
+## Download a file (not the whole branch) from below:
+
+| Filename | Quant type | File Size | Split | Description |
+| -------- | ---------- | --------- | ----- | ----------- |
+| [LFM2-350M-Extract-bf16.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Extract-GGUF/blob/main/LiquidAI_LFM2-350M-Extract-bf16.gguf) | bf16 | 0.71GB | false | Full BF16 weights. |
+| [LFM2-350M-Extract-Q8_0.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Extract-GGUF/blob/main/LiquidAI_LFM2-350M-Extract-Q8_0.gguf) | Q8_0 | 0.38GB | false | Extremely high quality, generally unneeded but max available quant. |
+| [LFM2-350M-Extract-Q6_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Extract-GGUF/blob/main/LiquidAI_LFM2-350M-Extract-Q6_K_L.gguf) | Q6_K_L | 0.31GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
+| [LFM2-350M-Extract-Q6_K.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Extract-GGUF/blob/main/LiquidAI_LFM2-350M-Extract-Q6_K.gguf) | Q6_K | 0.29GB | false | Very high quality, near perfect, *recommended*. |
+| [LFM2-350M-Extract-Q5_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Extract-GGUF/blob/main/LiquidAI_LFM2-350M-Extract-Q5_K_L.gguf) | Q5_K_L | 0.28GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
+| [LFM2-350M-Extract-Q5_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Extract-GGUF/blob/main/LiquidAI_LFM2-350M-Extract-Q5_K_M.gguf) | Q5_K_M | 0.26GB | false | High quality, *recommended*. |
+| [LFM2-350M-Extract-Q5_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Extract-GGUF/blob/main/LiquidAI_LFM2-350M-Extract-Q5_K_S.gguf) | Q5_K_S | 0.26GB | false | High quality, *recommended*. |
+| [LFM2-350M-Extract-Q4_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Extract-GGUF/blob/main/LiquidAI_LFM2-350M-Extract-Q4_K_L.gguf) | Q4_K_L | 0.25GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
+| [LFM2-350M-Extract-Q4_1.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Extract-GGUF/blob/main/LiquidAI_LFM2-350M-Extract-Q4_1.gguf) | Q4_1 | 0.24GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
+| [LFM2-350M-Extract-Q4_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Extract-GGUF/blob/main/LiquidAI_LFM2-350M-Extract-Q4_K_M.gguf) | Q4_K_M | 0.23GB | false | Good quality, default size for most use cases, *recommended*. |
+| [LFM2-350M-Extract-Q4_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Extract-GGUF/blob/main/LiquidAI_LFM2-350M-Extract-Q4_K_S.gguf) | Q4_K_S | 0.22GB | false | Slightly lower quality with more space savings, *recommended*. |
+| [LFM2-350M-Extract-Q4_0.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Extract-GGUF/blob/main/LiquidAI_LFM2-350M-Extract-Q4_0.gguf) | Q4_0 | 0.22GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
+| [LFM2-350M-Extract-IQ4_NL.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Extract-GGUF/blob/main/LiquidAI_LFM2-350M-Extract-IQ4_NL.gguf) | IQ4_NL | 0.22GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
+| [LFM2-350M-Extract-Q3_K_XL.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Extract-GGUF/blob/main/LiquidAI_LFM2-350M-Extract-Q3_K_XL.gguf) | Q3_K_XL | 0.22GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
+| [LFM2-350M-Extract-IQ4_XS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Extract-GGUF/blob/main/LiquidAI_LFM2-350M-Extract-IQ4_XS.gguf) | IQ4_XS | 0.21GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [LFM2-350M-Extract-Q3_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Extract-GGUF/blob/main/LiquidAI_LFM2-350M-Extract-Q3_K_L.gguf) | Q3_K_L | 0.20GB | false | Lower quality but usable, good for low RAM availability. |
+| [LFM2-350M-Extract-Q3_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Extract-GGUF/blob/main/LiquidAI_LFM2-350M-Extract-Q3_K_M.gguf) | Q3_K_M | 0.19GB | false | Low quality. |
+| [LFM2-350M-Extract-IQ3_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Extract-GGUF/blob/main/LiquidAI_LFM2-350M-Extract-IQ3_M.gguf) | IQ3_M | 0.18GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
+| [LFM2-350M-Extract-Q3_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Extract-GGUF/blob/main/LiquidAI_LFM2-350M-Extract-Q3_K_S.gguf) | Q3_K_S | 0.18GB | false | Low quality, not recommended. |
+| [LFM2-350M-Extract-IQ3_XS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Extract-GGUF/blob/main/LiquidAI_LFM2-350M-Extract-IQ3_XS.gguf) | IQ3_XS | 0.18GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
+| [LFM2-350M-Extract-Q2_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Extract-GGUF/blob/main/LiquidAI_LFM2-350M-Extract-Q2_K_L.gguf) | Q2_K_L | 0.18GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
+| [LFM2-350M-Extract-IQ3_XXS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Extract-GGUF/blob/main/LiquidAI_LFM2-350M-Extract-IQ3_XXS.gguf) | IQ3_XXS | 0.16GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
+| [LFM2-350M-Extract-Q2_K.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Extract-GGUF/blob/main/LiquidAI_LFM2-350M-Extract-Q2_K.gguf) | Q2_K | 0.16GB | false | Very low quality but surprisingly usable. |
+| [LFM2-350M-Extract-IQ2_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-350M-Extract-GGUF/blob/main/LiquidAI_LFM2-350M-Extract-IQ2_M.gguf) | IQ2_M | 0.14GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
+
+## Embed/output weights
+
+Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
+
+## Downloading using huggingface-cli
+
+<details>
+  <summary>Click to view download instructions</summary>
+
+First, make sure you have hugginface-cli installed:
+
+```
+pip install -U "huggingface_hub[cli]"
+```
+
+Then, you can target the specific file you want:
+
+```
+huggingface-cli download bartowski/LiquidAI_LFM2-350M-Extract-GGUF --include "LiquidAI_LFM2-350M-Extract-Q4_K_M.gguf" --local-dir ./
+```
+
+If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
+
+```
+huggingface-cli download bartowski/LiquidAI_LFM2-350M-Extract-GGUF --include "LiquidAI_LFM2-350M-Extract-Q8_0/*" --local-dir ./
+```
+
+You can either specify a new local-dir (LiquidAI_LFM2-350M-Extract-Q8_0) or download them all in place (./)
+
+</details>
+
+## ARM/AVX information
+
+Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.
+
+Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggml-org/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.
+
+As of llama.cpp build [b4282](https://github.com/ggml-org/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.
+
+Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggml-org/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.
+
+<details>
+  <summary>Click to view Q4_0_X_X information (deprecated</summary>
+
+I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.
+
+<details>
+  <summary>Click to view benchmarks on an AVX2 system (EPYC7702)</summary>
+
+| model                          |       size |     params | backend    | threads |          test |                  t/s |  % (vs Q4_0)  |
+| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |         pp512 |        204.03 ± 1.03 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |        pp1024 |        282.92 ± 0.19 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |        pp2048 |        259.49 ± 0.44 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |         tg128 |         39.12 ± 0.27 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |         tg256 |         39.31 ± 0.69 |          100% |
+| qwen2 3B Q4_0                  |   1.70 GiB |     3.09 B | CPU        |      64 |         tg512 |         40.52 ± 0.03 |          100% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |         pp512 |        301.02 ± 1.74 |          147% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |        pp1024 |        287.23 ± 0.20 |          101% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |        pp2048 |        262.77 ± 1.81 |          101% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |         tg128 |         18.80 ± 0.99 |           48% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |         tg256 |         24.46 ± 3.04 |           83% |
+| qwen2 3B Q4_K_M                |   1.79 GiB |     3.09 B | CPU        |      64 |         tg512 |         36.32 ± 3.59 |           90% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |         pp512 |        271.71 ± 3.53 |          133% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |        pp1024 |       279.86 ± 45.63 |          100% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |        pp2048 |        320.77 ± 5.00 |          124% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |         tg128 |         43.51 ± 0.05 |          111% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |         tg256 |         43.35 ± 0.09 |          110% |
+| qwen2 3B Q4_0_8_8              |   1.69 GiB |     3.09 B | CPU        |      64 |         tg512 |         42.60 ± 0.31 |          105% |
+
+Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation
+
+</details>
+
+</details>
+
+## Which file should I choose?
+
+<details>
+  <summary>Click here for details</summary>
+
+A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
+
+The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
+
+If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
+
+If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
+
+Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
+
+If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
+
+If you want to get more into the weeds, you can check out this extremely useful feature chart:
+
+[llama.cpp feature matrix](https://github.com/ggml-org/llama.cpp/wiki/Feature-matrix)
+
+But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
+
+These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
+
+</details>
+
+## Credits
+
+Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.
+
+Thank you ZeroWw for the inspiration to experiment with embed/output.
+
+Thank you to LM Studio for sponsoring my work.
+
+Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}